Training in progress, step 2740, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8b1559245f41d188181d6b9d0092f8ce476d0fbf69ecf90ff8a3c54ef660cb5
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d24f22c0ab4ad21937c14db9ea3282683b7ab5c773fd47bff7c49c8416b7f8bb
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d71f37ed7da35cab3fc85955319066a1d0751ae853d753172278078bedfd5b59
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9d7057839688d81937354c07a90bbd03a10be42f9b5d813a59ae57687cbd892
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2748,6 +2748,16 @@
|
|
| 2748 |
"mean_token_accuracy": 0.7586753875017166,
|
| 2749 |
"num_tokens": 12681486.0,
|
| 2750 |
"step": 2730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2751 |
}
|
| 2752 |
],
|
| 2753 |
"logging_steps": 10,
|
|
@@ -2767,7 +2777,7 @@
|
|
| 2767 |
"attributes": {}
|
| 2768 |
}
|
| 2769 |
},
|
| 2770 |
-
"total_flos": 6.
|
| 2771 |
"train_batch_size": 4,
|
| 2772 |
"trial_name": null,
|
| 2773 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5845333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2748 |
"mean_token_accuracy": 0.7586753875017166,
|
| 2749 |
"num_tokens": 12681486.0,
|
| 2750 |
"step": 2730
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"entropy": 0.9214616276323795,
|
| 2754 |
+
"epoch": 0.5845333333333333,
|
| 2755 |
+
"grad_norm": 0.2720118761062622,
|
| 2756 |
+
"learning_rate": 8.321488585053285e-05,
|
| 2757 |
+
"loss": 1.0133691787719727,
|
| 2758 |
+
"mean_token_accuracy": 0.7658515647053719,
|
| 2759 |
+
"num_tokens": 12728360.0,
|
| 2760 |
+
"step": 2740
|
| 2761 |
}
|
| 2762 |
],
|
| 2763 |
"logging_steps": 10,
|
|
|
|
| 2777 |
"attributes": {}
|
| 2778 |
}
|
| 2779 |
},
|
| 2780 |
+
"total_flos": 6.033431656914125e+16,
|
| 2781 |
"train_batch_size": 4,
|
| 2782 |
"trial_name": null,
|
| 2783 |
"trial_params": null
|